Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2126 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.9907. Min Act: -0.0001
Data Index: 82564 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1646. Min Range: -1.1646
Max Act: 1.1646. Min Act: -0.0001
Data Index: 576926 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8148. Min Act: -0.0001
Data Index: 1174836 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8136. Min Act: -0.0001
Data Index: 969751 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8557. Min Act: -0.0001
Data Index: 322498 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8908. Min Act: -0.0001
Data Index: 139413 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.7828. Min Act: -0.0001
Data Index: 1650691 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.7015. Min Act: -0.0001
Data Index: 1263248 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8010. Min Act: -0.0001
Data Index: 695295 (The Pile)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8020. Min Act: -0.0001
Data Index: 421429 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8699. Min Act: -0.0001
Data Index: 1606493 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8797. Min Act: -0.0001
Data Index: 687126 (The Pile)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.8337. Min Act: -0.0001
Data Index: 1994004 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.6855. Min Act: -0.0001
Data Index: 52408 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.7344. Min Act: -0.0001
Data Index: 1697608 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.7187. Min Act: -0.0001
Data Index: 1112114 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.6491. Min Act: -0.0001
Data Index: 625380 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.7347. Min Act: -0.0001
Data Index: 1641726 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.6651. Min Act: -0.0001
Data Index: 88843 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1646. Min Range: -1.1646
Max Act: 0.7712. Min Act: -0.0001
Data Index: 636349 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19